© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13936
    Prev
    Next
    INDEX
    Explanations

    makes/make/making

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    бак
    -0.10
    gow
    -0.09
    guan
    -0.08
    antin
    -0.08
    acun
    -0.08
    æīĢåij¨
    -0.08
    ambul
    -0.08
    ä¸įä¿Ĺ
    -0.08
    åĽłä¸ºä½ł
    -0.08
    aket
    -0.08
    POSITIVE LOGITS
    æľīå¿ħè¦ģ
    0.08
    ...
    0.07
    éĿŀ常éĢĤåIJĪ
    0.07
     impossible
    0.07
     возможнÑĭм
    0.07
     doubly
    0.06
    åħ¶ä¸º
    0.06
    对äºİä¸ĢäºĽ
    0.06
    éļ¾ä»¥
    0.06
     easier
    0.06
    Activations Density 0.077%

    No Known Activations